AI & ML
Towards Deep Learning-Based Linear Assignment Problem Solvers for Multi-Object Tracking
arXiv eess.SP0 views
arXiv:2611.24107v1 Announce Type: new Abstract: This paper proposes and evaluates deep learning (DL)-based linear assignment problem (LAP) solvers as a replacement for the classical Hungarian algorithm in multi-object tracking (MOT) systems. Three representative neural models are studied, namely a convolutional network (CNN), a graph neural network (GNN), and the graph-based linear assignment network (GLAN). A cost-matrix embedding is introduced so that a single model operates on cost matrices of any size, as required in MOT where the number of objects varies over time, without training a separate model for each input shape. Extensive simulations show that the embedding improves the accuracy of the neural solvers (i.e., CNN and GNN), while GLAN attains the best accuracy among them. These solvers are then integrated into a generalized labeled multi-Bernoulli (GLMB) tracker and evaluated on the WILDTRACK dataset, where GLAN yields tracking accuracy close to the Hungarian reference and comparable to recent DL-based trackers.
Source:https://arxiv.org/abs/2611.24107PreviousToward Massive MIMO HAPS Networks: Antenna Architectures and DesignNextConstellation Shaping for OFDM-ISAC Systems: A Systematic and Experimental Comparison
Related posts
Compute-in-Memory vs Von Neumann: Moving the Multiply to the Data
0dev.to AI
I Merely Am Someone Who Doesn't Touch Hot Stoves: Consciousness, Flores Speech Acts, the DSM Blindspot, and Why RLHF Is a Bad Actor
0dev.to AI
Storybrand Website Framework
0dev.to WebDev
Політика використання AI в команді
0dev.to WebDev
MrMWSK Studio: Web Apps
0dev.to WebDev
Indonesian Banks Rank Social Engineering as Top Threat: What It Means for Payments
0dev.to Security